Sotabase

Career

· Member Of Technical Staff, ReflectionAI2024–
· Research Intern, Waymo2024–2024
· Research Intern, Qualcomm2022–2022
· Ph.D. Student At Whiteson Research Lab (WhiRL), University of Oxford2020–2024
· Visiting Researcher, University of Michigan2018–2020
· Research Engineer, SK Telecom2017–2018
· Research Assistant, Aalto University2016–2016
· Machine Learning Engineer, Wolt2016–2016
· Research Assistant, Aalto University2015–2015
· Software Engineer, Apportable2014–2014

Publications (22)

Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation
Neural Information Processing Systems · 2019
244
cited
A Tutorial on Meta-Reinforcement Learning
Found. Trends Mach. Learn. · 2023
134
cited
Deep Reinforcement Learning for Multi-driver Vehicle Dispatching and Repositioning Problem
Industrial Conference on Data Mining · 2019
105
cited
Hypernetworks in Meta-Reinforcement Learning
Conference on Robot Learning · 2022
40
cited
Toward Multimodal Model-Agnostic Meta-Learning
arXiv.org · 2018
33
cited
Meta Continual Learning
arXiv.org · 2018
28
cited
Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design
Neural Information Processing Systems · 2023
19
cited
Recurrent Hypernetworks are Surprisingly Strong in Meta-RL
Neural Information Processing Systems · 2023
14
cited
On the Practical Consistency of Meta-Reinforcement Learning Algorithms
arXiv.org · 2021
11
cited
An Investigation of the Bias-Variance Tradeoff in Meta-Gradients
arXiv.org · 2022
7
cited
Distilling Morphology-Conditioned Hypernetworks for Efficient Universal Morphology Control
International Conference on Machine Learning · 2024
7
cited
Learning State Representations from Random Deep Action-conditional Predictions
Neural Information Processing Systems · 2021
6
cited
Adaptive Pairwise Weights for Temporal Credit Assignment
AAAI Conference on Artificial Intelligence · 2021
5
cited
Deconfounding Imitation Learning with Variational Inference
Trans. Mach. Learn. Res. · 2022
4
cited
Action-Constrained Imitation Learning
International Conference on Machine Learning · 2025
3
cited
Pairwise Weights for Temporal Credit Assignment
arXiv.org · 2021
3
cited
SplAgger: Split Aggregation for Meta-Reinforcement Learning
RLJ · 2024
2
cited
A Bayesian Solution To The Imitation Gap
arXiv.org · 2024
1
cited
IGDrivSim: A Benchmark for the Imitation Gap in Autonomous Driving
IEEE/RJS International Conference on Intelligent RObots and Systems · 2024
1
cited
Model-Agnostic Meta-Learning for Multimodal Task Distributions
2018
1
cited
Sotabase
Risto Vuorio | Researcher Profile | Sotabase | Sotabase